{"id":"W4287816198","doi":"10.48550/arxiv.2004.04468","title":"A Multilingual Study of Multi-Sentence Compression using Word\\n Vertex-Labeled Graphs and Integer Linear Programming","year":2020,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Grammaticality; Computer science; Automatic summarization; Sentence; Natural language processing; Artificial intelligence; Integer programming; Word (group theory); Graph; Algorithm; Theoretical computer science; Grammar; Mathematics; Linguistics","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001914624,0.0006934006,0.00053025,0.00174582,0.0005904653,0.001417403,0.0008842196,0.0006220269,0.002713736],"category_scores_gemma":[0.009859138,0.00032974,0.0006444919,0.002130845,0.0008996118,0.002532462,0.000837597,0.001299913,0.0005611885],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001516491,"about_ca_system_score_gemma":0.0009588927,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009166889,"about_ca_topic_score_gemma":0.01113691,"domain_scores_codex":[0.9981216,0.001028657,0.00008387568,0.0003714594,0.000293562,0.0001009188],"domain_scores_gemma":[0.989876,0.008167567,0.000513292,0.0005315558,0.0007374631,0.0001741257],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0009471367,0.0006775365,0.005984775,0.0009816734,0.0002792482,0.0005884735,0.0008009335,0.3048782,0.01378379,0.04232072,0.009250511,0.619507],"study_design_scores_gemma":[0.00003714516,0.0002376797,0.001288207,0.00002111784,0.00005358226,0.0001656971,0.0001854437,0.9698093,0.008816618,0.01455108,0.004798555,0.00003559253],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1612201,0.003085351,0.8222011,0.001294223,0.000177009,0.0001661807,0.0006134435,0.002556422,0.00868617],"genre_scores_gemma":[0.6258156,0.0009916046,0.365722,0.0002661105,0.0003203831,0.0001212381,0.001774781,0.0006185702,0.004369729],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.009166889,"threshold_uncertainty_score":0.0182271,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1189421988582682,"score_gpt":0.2663279437168967,"score_spread":0.1473857448586285,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}